检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Zhang, Jiyuan Feng, Yang Wang, Dong Wang, Yang Abel, Andrew Zhang, Shiyue Zhang, Andi Tsinghua University Riit China Peking University Shool of Software & Microelectronics China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Cas Huilan Limited Beijing China Beijing University of Posts and Telecommunications China Xi'an Jiaotong-Liverpool University China

It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. In addition, it is found that the memory mechanism provides interesting flexibility that can be used to generate poems with different styles. Copyright © 2017, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memory-augmented neural machine translation

arXiv

引用

arXiv 2017年

作者： Feng, Yang Zhang, Shiyue Zhang, Andi Wang, Dong Abel, Andrew Center for Speech and Language Technologies RIIT Tsinghua University Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing University of Posts and Telecommunications China Huilan Corporation Beijing China Xi'An Jiaotong Liverpool-University Suzhou China

Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memory-augmented NMT (M-NMT) architecture, which stores knowledge about how words (usually infrequently encountered ones) should be translated in a memory and then utilizes them to assist the neural model. We use this memory mechanism to combine the knowledge learned from a conventional statistical machine translation system and the rules learned by an NMT system, and also propose a solution for out-of-vocabulary (OOV) words based on this framework. Our experiments on two Chinese-English translation tasks demonstrated that the M-NMT architecture outperformed the NMT baseline by 9.0 and 2.7 BLEU points on the two tasks, respectively. Additionally, we found this architecture resulted in a much more effective OOV treatment compared to competitive methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Firefly algorithm guided by general centre particle and its application in node localisation of wireless sensor networks

引用

International Journal of Wireless and Mobile computing 2017年第2期13卷 122-130页

作者： Lv, Li Tian, Hongmin Zhao, Jia Xie, Zhifeng Fan, Tanghuai Han, Longzhe National and Provincial Joint Engineering Lab. for the Hydr. Eng. Safety and Efficient Utilization of Water Resources of Poyang Lake Basin Nanchang Institute of Technology Nanchang330099 China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China Labor Union Nanchang Institute of Technology Nanchang330099 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang330099 China

Firefly algorithm (FA) is a kind of swarm intelligence algorithm that was developed by simulating the behaviour of the flashing of fireflies. However, the population uses only the advantage of the better particles' information to complete optimisation without using the comprehensive information of the population effectively. So, this paper proposes an improved FA, namely firefly algorithm guided by general centre particle (GCPFA), in which the General Centre Particle (GCP) was generated by sharing each particle's historically optimal position information, and each particle would learn from GCP after they learned from the other particles with better performances. The simulation results on 12 benchmark test functions also revealed GCPFA's superiority to the other six famous FAs. In order to improve the unreasonable distribution of sensor nodes randomly and improve the network coverage rate, the above algorithm is applied to optimise the coverage of wireless sensor networks and achieve better optimisation effect. Copyright © 2017 Inderscience Enterprises Ltd.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Occlusion-free Face Alignment: Deep Regression Networks Coupled with De-corrupt AutoEncoders

Occlusion-free Face Alignment: Deep Regression Networks Coup...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Jie Zhang Meina Kan Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781467388528

Face alignment or facial landmark detection plays an important role in many computer vision applications, e.g., face recognition, facial expression recognition, face animation, etc. However, the performance of face alignment system degenerates severely when occlusions occur. In this work, we propose a novel face alignment method, which cascades several Deep Regression networks coupled with De-corrupt Autoencoders (denoted as DRDA) to explicitly handle partial occlusion problem. Different from the previous works that can only detect occlusions and discard the occluded parts, our proposed de-corrupt autoencoder network can automatically recover the genuine appearance for the occluded parts and the recovered parts can be leveraged together with those non-occluded parts for more accurate alignment. By coupling de-corrupt autoencoders with deep regression networks, a deep alignment model robust to partial occlusions is achieved. Besides, our method can localize occluded regions rather than merely predict whether the landmarks are occluded. Experiments on two challenging occluded face datasets demonstrate that our method significantly outperforms the state-of-the-art methods.

关键词： Occlusion Face Face occluding landmarks Alignment Regression (Psychology) Facial Recognition images computer vision coupling

来源：评论

学校读者我要写书评

暂无评论

多组学基因大数据与精准医学

多组学基因大数据与精准医学

引用

浙江省生物信息学学会第五届学术年会暨大数据时代精准医学国际学术研讨会

作者： Yi Zhao Bioinformatics Research Group Key Laboratory of Intelligent Information ProcessingAdvanced Computing Research LaboratoryInstitute of Computing TechnologyChineseAcademy of Sciences LuoYang Branch of Institute of Computing Technology Chinese Academy of Sciences

伴随着高通量测序技术等生物技术的发展,基因组、转录组、表观组、蛋白组、代谢组、微生物组、暴露组等多组学测序数据可以在几天之内迅速产出,并被广泛应用于精准医学的研究和临床应用,这些庞大而复杂的数据不但构成了精确医学所需要... 详细信息

伴随着高通量测序技术等生物技术的发展,基因组、转录组、表观组、蛋白组、代谢组、微生物组、暴露组等多组学测序数据可以在几天之内迅速产出,并被广泛应用于精准医学的研究和临床应用,这些庞大而复杂的数据不但构成了精确医学所需要的关键信息,而且也是该领域内增长最快的数据类型。当前,精准医学计划在多个国家陆续启动,各国科学家们正致力于收集十万、百万人群的基因组信息用来构建权威、且全新的人口健康大数据知识体系。在这样的时代背景下,作为人口大国,中国精准医学迫切的需要建立属于中国人自己的基因数据库。2016年,中国科技部将"精准医学研究"列为重大研究计划,中科院也于2016年启动中国人群精准医学研究计划,4年内预计完成4000志愿者的DNA样本和多种表现型数据的采集。对此,我们可以预见,随着大队列研究的开展,以基因组为代表的多组学大数据仍将会不断产生,但是这些组学大数据本身并不能产生价值,其价值在于与疾病表型等其他信息进行关联分析、挖掘并转换为知识,才能进一步被应用于医疗及健康决策。因此,促进大数据到知识的转化,构建基因大数据研究与应用的一体化平台体系,才是精准医学到临床的关键一步,其将会被应用于疾病的早期筛查、分子分型、个体化治疗、疗效预测及监控等多个临床决策场景。多组学精准医学大数据的发展和研究也面临着一些挑战,例如:数据共享与安全隐私问题、多维度组学数据的整合分析问题、生物信息数据分析方法的标准化以及解读规范化等等问题。因此,需要更多国家政策的支持、需要IT及人工智能等领域的学者贡献力量、需要各个领域的专家来制定行业标准,最终推动精准医疗向自动化,智能化,标准化,简单化方向发展。

关键词：精准医学多组学大数据

来源：评论

学校读者我要写书评

暂无评论

Interactive attention for neural machine translation 26

Interactive attention for neural machine translation

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Meng, Fandong Lu, Zhengdong Li, Hang Liu, Qun AI Platform Department Tencent Technology Co. Ltd. China Noah's Ark Lab. Huawei Technologies China ADAPT Centre School of Computing Dublin City University Ireland Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Ireland

ISBN: (纸本)9784879747020

Conventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence. By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder (Bahdanau et al., 2015), the attention mechanism has greatly enhanced state-of-the-art NMT. In this paper, we propose a new attention mechanism, called INTERACTIVE ATTENTION, which models the interaction between the decoder and the representation of source sentence during translation by both reading and writing operations. INTERACTIVE ATTENTION can keep track of the interaction history and therefore improve the translation performance. Experiments on NIST Chinese-English translation task show that INTERACTIVE ATTENTION can achieve significant improvements over both the previous attention-based NMT baseline and some state-of-the-art variants of attention-based NMT (i.e., coverage models (Tu et al., 2016)). And neural machine translator with our INTERACTIVE ATTENTION can outperform the open source attention-based NMT system Groundhog by 4.22 BLEU points and the open source phrase-based system Moses by 3.94 BLEU points averagely on multiple test sets. © 1963-2018 ACL.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Neural network for heterogeneous annotations

Neural network for heterogeneous annotations

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Chen, Hongshen Zhang, Yue Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Singapore University of Technology and Design Singapore ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9781945626258

Multiple treebanks annotated under heterogeneous standards give rise to the research question of best utilizing multiple resources for improving statistical models. Prior research has focused on discrete models, leveraging stacking and multi-view learning to address the problem. In this paper, we empirically investigate heterogeneous annotations using neural network models, building a neural network counterpart to discrete stacking and multi-view learning, respectively, finding that neural models have their unique advantages thanks to the freedom from manual feature engineering. Neural model achieves not only better accuracy improvements, but also an order of magnitude faster speed compared to its discrete baseline, adding little time cost compared to a neural model trained on a single treebank. © 2016 Association for Computational Linguistics

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Learning label-Specific Features and Class-Dependent labels for Multi-label Classification

引用

IEEE Transactions on Knowledge and Data Engineering 2016年第99期PP卷 3309-3323页

作者： Huang, Jun Li, Guorong Huang, Qingming Wu, Xindong School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing101480 China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Department of Computer Science University of Vermont 33 Colchester Avenue BurlingtonVT05405 United States

Binary Relevance is a well-known framework for multi-label classification, which considers each class label as a binary classification problem. Many existing multi-label algorithms are constructed within this framework and utilize identical data representation in the discrimination of all the class labels. In multi-label classification, however, each class label might be determined by some specific characteristics of its own. In this paper, we seek to learn label-specific data representation for each class label, which is composed of label-specific features. Our proposed method LLSF can not only be utilized for multi-label classification directly, but also be applied as a feature selection method for multi-label learning and a general strategy to improve multi-label classification algorithms comprising a number of binary classifiers. Inspired by the research works on modeling high-order label correlations, we further extend LLSF to learn class-Dependent labels in a sparse stacking way, denoted as LLSFDL. It incorporates both second-order and high-order label correlations. A comparative study with the state-of-the-art approaches manifests the effectiveness and efficiency of our proposed methods. © 2016 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Construction of One-Gray Weight Codes and Two-Gray Weight Codes over Z4+uZ4

引用

Journal of Systems Science & Complexity 2016年第5期29卷 1472-1484页

作者： SHI Minjia WANG Dandan GAO Jian WU Bo Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei 230039 China National Mobile Communications Research Laboratory Southeast University Nanjing 210096China School of Mathematical Sciences Anhui University Hefei 230601 China. School of Science Shandong University of Technology Zibo 255091 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Bcijing 100093 China

This paper firstly gives some necessary conditions on one-Gray weight linear codes. And then we use these results to construct several classes of one-Gray weight linear codes over Z_4 +uZ_4(u^2=u) with type 16^(k_1)8^(k_2)8^(k_3)4^(k_4)4^(k_5)4^(k_6)2^(k_7)2^(k_8) based on a distance-preserving Gray map from(Z4 + u Z4)n to Z2n4. Secondly, the authors use the similar approach to do works on two-Gray(projective) weight linear codes. Finally, some examples are given to illustrate the construction methods.

关键词： Generator matrix Gray map linear code one-Gray weight code two-Gray weight code

来源：评论

学校读者我要写书评

暂无评论

One-shot fine-grained instance retrieval

arXiv

引用

arXiv 2017年

作者： Yao, Hantao Zhang, Shiliang Zhang, Yongdong Li, Jintao Tian, Qi Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Electronic Engineering and Computer Science Peking University Beijing100871 China Department of Computer Science University of Texas at San Antonio San Antonio United States

Fine-Grained Visual Categorization (FGVC) has achieved significant progress recently. However, the number of fine-grained species could be huge and dynamically increasing in real scenarios, making it difficult to recognize unseen objects under the current FGVC framework. This raises an open issue to perform large-scale fine-grained identification without a complete training set. Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR). "One-Shot" denotes the ability of identifying unseen objects through a fine-grained retrieval task assisted with an incomplete auxiliary training set. This paper first presents the detailed description to OSFGIR task and our collected OSFGIR-378K dataset. Next, we propose the Convolutional and Normalization Networks (CN-Nets) learned on the auxiliary dataset to generate a concise and discriminative representation. Finally, we present a coarse-to-fine retrieval framework consisting of three components, i.e., coarse retrieval, fine-grained retrieval, and query expansion, respectively. The framework progressively retrieves images with similar semantics, and performs fine-grained identification. Experiments show our OSFGIR framework achieves significantly better accuracy and efficiency than existing FGVC and image retrieval methods, thus could be a better solution for large-scale fine-grained object identification. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：